storj/satellite/satellitedb/migrate_test.go

274 lines
7.4 KiB
Go
Raw Normal View History

2019-02-14 21:55:21 +00:00
// Copyright (C) 2019 Storj Labs, Inc.
// See LICENSE for copying information.
package satellitedb_test
import (
"context"
2019-02-14 21:55:21 +00:00
"fmt"
"io/ioutil"
"path/filepath"
"strconv"
"strings"
"testing"
"time"
2019-02-14 21:55:21 +00:00
"github.com/lib/pq"
2019-02-14 21:55:21 +00:00
"github.com/stretchr/testify/require"
"github.com/zeebo/errs"
"go.uber.org/zap"
2019-02-14 21:55:21 +00:00
"go.uber.org/zap/zaptest"
"golang.org/x/sync/errgroup"
"storj.io/common/testcontext"
"storj.io/storj/private/dbutil/dbschema"
"storj.io/storj/private/dbutil/pgutil"
"storj.io/storj/private/dbutil/pgutil/pgtest"
"storj.io/storj/private/dbutil/tempdb"
satellite/satellitedb: unexport satellitedb.DB Backstory: I needed a better way to pass around information about the underlying driver and implementation to all the various db-using things in satellitedb (at least until some new "cockroach driver" support makes it to DBX). After hitting a few dead ends, I decided I wanted to have a type that could act like a *dbx.DB but which would also carry information about the implementation, etc. Then I could pass around that type to all the things in satellitedb that previously wanted *dbx.DB. But then I realized that *satellitedb.DB was, essentially, exactly that already. One thing that might have kept *satellitedb.DB from being directly usable was that embedding a *dbx.DB inside it would make a lot of dbx methods publicly available on a *satellitedb.DB instance that previously were nicely encapsulated and hidden. But after a quick look, I realized that _nothing_ outside of satellite/satellitedb even needs to use satellitedb.DB at all. It didn't even need to be exported, except for some trivially-replaceable code in migrate_postgres_test.go. And once I made it unexported, any concerns about exposing new methods on it were entirely moot. So I have here changed the exported *satellitedb.DB type into the unexported *satellitedb.satelliteDB type, and I have changed all the places here that wanted raw dbx.DB handles to use this new type instead. Now they can just take a gander at the implementation member on it and know all they need to know about the underlying database. This will make it possible for some other pending code here to differentiate between postgres and cockroach backends. Change-Id: I27af99f8ae23b50782333da5277b553b34634edc
2019-12-14 02:29:54 +00:00
"storj.io/storj/private/migrate"
2019-02-14 21:55:21 +00:00
"storj.io/storj/satellite/satellitedb"
"storj.io/storj/satellite/satellitedb/dbx"
2019-02-14 21:55:21 +00:00
)
// loadSnapshots loads all the dbschemas from testdata/postgres.*
func loadSnapshots(ctx context.Context, connstr, dbxscript string) (*dbschema.Snapshots, *dbschema.Schema, error) {
2019-02-14 21:55:21 +00:00
snapshots := &dbschema.Snapshots{}
// find all postgres sql files
matches, err := filepath.Glob("testdata/postgres.*")
if err != nil {
return nil, nil, err
2019-02-14 21:55:21 +00:00
}
snapshots.List = make([]*dbschema.Snapshot, len(matches))
var group errgroup.Group
for i, match := range matches {
i, match := i, match
group.Go(func() error {
versionStr := match[19 : len(match)-4] // hack to avoid trim issues with path differences in windows/linux
version, err := strconv.Atoi(versionStr)
if err != nil {
return errs.New("invalid testdata file %q: %v", match, err)
}
2019-02-14 21:55:21 +00:00
scriptData, err := ioutil.ReadFile(match)
if err != nil {
return errs.New("could not read testdata file for version %d: %v", version, err)
}
2019-02-14 21:55:21 +00:00
snapshot, err := loadSnapshotFromSQL(ctx, connstr, string(scriptData))
if err != nil {
if pqErr, ok := err.(*pq.Error); ok && pqErr.Detail != "" {
return fmt.Errorf("Version %d error: %v\nDetail: %s\nHint: %s", version, pqErr, pqErr.Detail, pqErr.Hint)
}
return fmt.Errorf("Version %d error: %+v", version, err)
}
snapshot.Version = version
2019-02-14 21:55:21 +00:00
snapshots.List[i] = snapshot
return nil
})
}
var dbschema *dbschema.Schema
group.Go(func() error {
var err error
dbschema, err = loadSchemaFromSQL(ctx, connstr, dbxscript)
return err
})
if err := group.Wait(); err != nil {
return nil, nil, err
2019-02-14 21:55:21 +00:00
}
snapshots.Sort()
return snapshots, dbschema, nil
2019-02-14 21:55:21 +00:00
}
// loadSnapshotFromSQL inserts script into connstr and loads schema.
func loadSnapshotFromSQL(ctx context.Context, connstr, script string) (_ *dbschema.Snapshot, err error) {
db, err := tempdb.OpenUnique(ctx, connstr, "load-schema")
if err != nil {
return nil, err
}
defer func() { err = errs.Combine(err, db.Close()) }()
_, err = db.ExecContext(ctx, script)
if err != nil {
return nil, err
}
snapshot, err := pgutil.QuerySnapshot(ctx, db)
if err != nil {
return nil, err
}
snapshot.Script = script
return snapshot, nil
}
2019-02-14 21:55:21 +00:00
const newDataSeparator = `-- NEW DATA --`
func newData(snap *dbschema.Snapshot) string {
tokens := strings.SplitN(snap.Script, newDataSeparator, 2)
if len(tokens) != 2 {
return ""
}
return tokens[1]
}
// loadSchemaFromSQL inserts script into connstr and loads schema.
func loadSchemaFromSQL(ctx context.Context, connstr, script string) (_ *dbschema.Schema, err error) {
db, err := tempdb.OpenUnique(ctx, connstr, "load-schema")
if err != nil {
return nil, err
}
defer func() { err = errs.Combine(err, db.Close()) }()
_, err = db.ExecContext(ctx, script)
if err != nil {
return nil, err
}
return pgutil.QuerySchema(ctx, db)
}
func TestMigrateCockroach(t *testing.T) {
if *pgtest.CrdbConnStr == "" {
t.Skip("Cockroach flag missing, example: -cockroach-test-db=" + pgtest.DefaultCrdbConnStr)
}
t.Parallel()
migrateTest(t, *pgtest.CrdbConnStr)
}
2019-02-14 21:55:21 +00:00
func TestMigratePostgres(t *testing.T) {
2019-04-26 14:39:11 +01:00
if *pgtest.ConnStr == "" {
t.Skip("Postgres flag missing, example: -postgres-test-db=" + pgtest.DefaultConnStr)
2019-02-14 21:55:21 +00:00
}
t.Parallel()
migrateTest(t, *pgtest.ConnStr)
}
func BenchmarkSetup_Postgres(b *testing.B) {
if *pgtest.ConnStr == "" {
b.Skip("Postgres flag missing, example: -postgres-test-db=" + pgtest.DefaultConnStr)
}
b.Run("merged", func(b *testing.B) {
benchmarkSetup(b, *pgtest.ConnStr, true)
})
b.Run("separate", func(b *testing.B) {
benchmarkSetup(b, *pgtest.ConnStr, false)
})
}
func BenchmarkSetup_Cockroach(b *testing.B) {
if *pgtest.CrdbConnStr == "" {
b.Skip("Cockroach flag missing, example: -cockroach-test-db=" + pgtest.DefaultCrdbConnStr)
}
b.Run("merged", func(b *testing.B) {
benchmarkSetup(b, *pgtest.CrdbConnStr, true)
})
b.Run("separate", func(b *testing.B) {
benchmarkSetup(b, *pgtest.CrdbConnStr, false)
})
}
func benchmarkSetup(b *testing.B, connStr string, merged bool) {
for i := 0; i < b.N; i++ {
func() {
ctx := context.Background()
log := zap.NewNop()
// create tempDB
tempDB, err := tempdb.OpenUnique(ctx, connStr, "migrate")
require.NoError(b, err)
defer func() { require.NoError(b, tempDB.Close()) }()
// create a new satellitedb connection
db, err := satellitedb.New(log, tempDB.ConnStr, satellitedb.Options{})
require.NoError(b, err)
defer func() { require.NoError(b, db.Close()) }()
if merged {
err = db.TestingCreateTables(ctx)
require.NoError(b, err)
} else {
err = db.CreateTables(ctx)
require.NoError(b, err)
}
}()
}
}
satellite/satellitedb: unexport satellitedb.DB Backstory: I needed a better way to pass around information about the underlying driver and implementation to all the various db-using things in satellitedb (at least until some new "cockroach driver" support makes it to DBX). After hitting a few dead ends, I decided I wanted to have a type that could act like a *dbx.DB but which would also carry information about the implementation, etc. Then I could pass around that type to all the things in satellitedb that previously wanted *dbx.DB. But then I realized that *satellitedb.DB was, essentially, exactly that already. One thing that might have kept *satellitedb.DB from being directly usable was that embedding a *dbx.DB inside it would make a lot of dbx methods publicly available on a *satellitedb.DB instance that previously were nicely encapsulated and hidden. But after a quick look, I realized that _nothing_ outside of satellite/satellitedb even needs to use satellitedb.DB at all. It didn't even need to be exported, except for some trivially-replaceable code in migrate_postgres_test.go. And once I made it unexported, any concerns about exposing new methods on it were entirely moot. So I have here changed the exported *satellitedb.DB type into the unexported *satellitedb.satelliteDB type, and I have changed all the places here that wanted raw dbx.DB handles to use this new type instead. Now they can just take a gander at the implementation member on it and know all they need to know about the underlying database. This will make it possible for some other pending code here to differentiate between postgres and cockroach backends. Change-Id: I27af99f8ae23b50782333da5277b553b34634edc
2019-12-14 02:29:54 +00:00
// satelliteDB provides access to certain methods on a *satellitedb.satelliteDB
// instance, since that type is not exported.
type satelliteDB interface {
TestDBAccess() *dbx.DB
PostgresMigration() *migrate.Migration
}
func migrateTest(t *testing.T, connStr string) {
ctx := testcontext.NewWithTimeout(t, 5*time.Minute)
defer ctx.Cleanup()
log := zaptest.NewLogger(t)
// create tempDB
tempDB, err := tempdb.OpenUnique(ctx, connStr, "migrate")
require.NoError(t, err)
defer func() { require.NoError(t, tempDB.Close()) }()
2019-02-14 21:55:21 +00:00
// create a new satellitedb connection
db, err := satellitedb.New(log, tempDB.ConnStr, satellitedb.Options{})
require.NoError(t, err)
defer func() { require.NoError(t, db.Close()) }()
2019-02-14 21:55:21 +00:00
// we need raw database access unfortunately
satellite/satellitedb: unexport satellitedb.DB Backstory: I needed a better way to pass around information about the underlying driver and implementation to all the various db-using things in satellitedb (at least until some new "cockroach driver" support makes it to DBX). After hitting a few dead ends, I decided I wanted to have a type that could act like a *dbx.DB but which would also carry information about the implementation, etc. Then I could pass around that type to all the things in satellitedb that previously wanted *dbx.DB. But then I realized that *satellitedb.DB was, essentially, exactly that already. One thing that might have kept *satellitedb.DB from being directly usable was that embedding a *dbx.DB inside it would make a lot of dbx methods publicly available on a *satellitedb.DB instance that previously were nicely encapsulated and hidden. But after a quick look, I realized that _nothing_ outside of satellite/satellitedb even needs to use satellitedb.DB at all. It didn't even need to be exported, except for some trivially-replaceable code in migrate_postgres_test.go. And once I made it unexported, any concerns about exposing new methods on it were entirely moot. So I have here changed the exported *satellitedb.DB type into the unexported *satellitedb.satelliteDB type, and I have changed all the places here that wanted raw dbx.DB handles to use this new type instead. Now they can just take a gander at the implementation member on it and know all they need to know about the underlying database. This will make it possible for some other pending code here to differentiate between postgres and cockroach backends. Change-Id: I27af99f8ae23b50782333da5277b553b34634edc
2019-12-14 02:29:54 +00:00
rawdb := db.(satelliteDB).TestDBAccess()
2019-02-14 21:55:21 +00:00
snapshots, dbxschema, err := loadSnapshots(ctx, connStr, rawdb.Schema())
require.NoError(t, err)
var finalSchema *dbschema.Schema
2019-02-14 21:55:21 +00:00
// get migration for this database
satellite/satellitedb: unexport satellitedb.DB Backstory: I needed a better way to pass around information about the underlying driver and implementation to all the various db-using things in satellitedb (at least until some new "cockroach driver" support makes it to DBX). After hitting a few dead ends, I decided I wanted to have a type that could act like a *dbx.DB but which would also carry information about the implementation, etc. Then I could pass around that type to all the things in satellitedb that previously wanted *dbx.DB. But then I realized that *satellitedb.DB was, essentially, exactly that already. One thing that might have kept *satellitedb.DB from being directly usable was that embedding a *dbx.DB inside it would make a lot of dbx methods publicly available on a *satellitedb.DB instance that previously were nicely encapsulated and hidden. But after a quick look, I realized that _nothing_ outside of satellite/satellitedb even needs to use satellitedb.DB at all. It didn't even need to be exported, except for some trivially-replaceable code in migrate_postgres_test.go. And once I made it unexported, any concerns about exposing new methods on it were entirely moot. So I have here changed the exported *satellitedb.DB type into the unexported *satellitedb.satelliteDB type, and I have changed all the places here that wanted raw dbx.DB handles to use this new type instead. Now they can just take a gander at the implementation member on it and know all they need to know about the underlying database. This will make it possible for some other pending code here to differentiate between postgres and cockroach backends. Change-Id: I27af99f8ae23b50782333da5277b553b34634edc
2019-12-14 02:29:54 +00:00
migrations := db.(satelliteDB).PostgresMigration()
for i, step := range migrations.Steps {
tag := fmt.Sprintf("#%d - v%d", i, step.Version)
2019-02-14 21:55:21 +00:00
// run migration up to a specific version
err := migrations.TargetVersion(step.Version).Run(ctx, log.Named("migrate"))
require.NoError(t, err, tag)
2019-02-14 21:55:21 +00:00
// find the matching expected version
expected, ok := snapshots.FindVersion(step.Version)
require.True(t, ok, "Missing snapshot v%d. Did you forget to add a snapshot for the new migration?", step.Version)
2019-02-14 21:55:21 +00:00
// insert data for new tables
if newdata := newData(expected); newdata != "" {
_, err = rawdb.ExecContext(ctx, newdata)
require.NoError(t, err, tag)
}
2019-02-14 21:55:21 +00:00
// load schema from database
currentSchema, err := pgutil.QuerySchema(ctx, rawdb)
require.NoError(t, err, tag)
2019-02-14 21:55:21 +00:00
// we don't care changes in versions table
currentSchema.DropTable("versions")
2019-02-14 21:55:21 +00:00
// load data from database
currentData, err := pgutil.QueryData(ctx, rawdb, currentSchema)
require.NoError(t, err, tag)
2019-02-14 21:55:21 +00:00
// verify schema and data
require.Equal(t, expected.Schema, currentSchema, tag)
require.Equal(t, expected.Data, currentData, tag)
2019-02-14 21:55:21 +00:00
// keep the last version around
finalSchema = currentSchema
}
2019-02-14 21:55:21 +00:00
// verify that we also match the dbx version
require.Equal(t, dbxschema, finalSchema, "dbx")
2019-02-14 21:55:21 +00:00
}